Loading [a11y]/accessibility-menu.js
Clustering of matched features and gradient matching for mixed-resolution video super-resolution | IEEE Conference Publication | IEEE Xplore

Clustering of matched features and gradient matching for mixed-resolution video super-resolution


Abstract:

This work presents a novel technique for image reconstruction applied to mixed-resolution video super-resolution. We segment an image into patches defined by the clusteri...Show More

Abstract:

This work presents a novel technique for image reconstruction applied to mixed-resolution video super-resolution. We segment an image into patches defined by the clustering of a vector flow generated from matching SIFT features. We reconstruct the segmented image by applying image projective transformation to a reference image. By varying the number of clusters, we composed a sequence of reconstructed images, which are then used to compose a codebook, through gradient matching. This idea is extended to use low and high-resolution image pairs for super-resolution. Our results indicate a 1.4dB gain, on average, over the use of overlapped-block motion-compensation (OBMC).
Date of Conference: 24-27 May 2015
Date Added to IEEE Xplore: 30 July 2015
Electronic ISBN:978-1-4799-8391-9

ISSN Information:

Conference Location: Lisbon, Portugal

References

References is not available for this document.